Khan, Fazeel Ahmed and Abubakar, Adamu (2020) Machine translation in natural language processing by implementing artificial neural network modelling techniques: an Analysis. International Journal on Perceptive and Cognitive Computing, 6 (1). pp. 9-18. E-ISSN 2462-229X
PDF
Restricted to Registered users only Download (525kB) | Request a copy |
Abstract
Natural Language Processing is emerging with more efficient algorithms to perform detailed analysis and synthesis on different languages and speech translation with techniques from computer science. Machine translation is emerging from Statistical Machine Translation to a more efficient and robust oriented deep learning based Neural Machine Translation. The limitation in Statistical based MT opens a new spectrum of research in NMT to resolve the existing problemsand explore NMT potential in MT research. This paper comprehensively analyses various NMT models proposed in recent years and their contribution in resolving language translation issues. It also discusses on some NMT based open-source toolkits introduced in recent year and the feature implemented in these toolkits. It also analyses the potential of these toolkits to comply with research in language translation particularly in NMT based techniques
Item Type: | Article (Journal) |
---|---|
Additional Information: | 7132/81268 |
Uncontrolled Keywords: | Statistical Machine Translation, Neural Machine Translation, Natural Language Processing, Artificial Neural Network, Machine Translation |
Subjects: | Q Science > Q Science (General) > Q300 Cybernetics > Q350 Information theory |
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): | Kulliyyah of Information and Communication Technology > Department of Computer Science Kulliyyah of Information and Communication Technology > Department of Computer Science |
Depositing User: | Dr Adamu Abubakar |
Date Deposited: | 06 Jul 2020 15:50 |
Last Modified: | 06 Jul 2020 15:50 |
URI: | http://irep.iium.edu.my/id/eprint/81268 |
Actions (login required)
View Item |